Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chatbots: Still dumb after all these years

mindmatters.ai

Post reply on HN
Print view View original

71–80 of 426 posts

Re: Chatbots: Still dumb after all these years

#71

Post by hotpotamus »

klyrs wrote: post #30
hotpotamus wrote: post #23

Earlier quoted context omitted.

I'm not trying to be mean or break any HN rules, but did you read the article? It basically covers what you asked and was quite a revelation to me. Others in here point out that GPT-3 is not a chatbot which is good info, but I also wonder if there is anything out there that can even "remember" the context of a conversation it's supposed to be having. Particularly interesting is the question from the article, "who is…

Hidden in my comment is a question: has anybody even tried to included previous lines into the prompt, and does that not help? Asking here because there are a lot of ML nerds who could probably do a proof of concept in a few hours, if not a few lines of code, so there's a decent chance I'll get an informed response.

My guess (and I'm certainly no expert here) is that not only have people put a few hours or lines of code into it, but probably many a PHD thesis as well. It's an intensely researched topic which makes the article even more surprising to me.

Re: Chatbots: Still dumb after all these years

#72

Post by kingkawn »

tomrod wrote: post #40
kingkawn wrote: post #32

Earlier quoted context omitted.

That interpretation of communication is how we develop and craft the personalities of children. There is nothing about our reaction to the pre-conscious language these bots are displaying that doesn’t fall in line with our own normal development patterns. And in the long run the same desire will lead us to develop bots that are capable of thinking.

> There is nothing about our reaction to the pre-conscious language these bots are displaying that doesn’t fall in line with our own normal development patterns Well... yes and no. Deployed models typically learn in a defined pattern, if at all. Various forms of data freshness, etc. to develop. But the chatbots don't have good history recall, typically, and know that what you mentioned 50 messages ago is relevant to…

You misunderstood what I was saying. I know the chatbot itself is not structured as we are. I’m saying that our reactions to them are the standard tools of mind-building that we apply to our own kids (and pets).

Re: Chatbots: Still dumb after all these years

#73

Post by hdjjhhvvhga »

pwinnski wrote: post #13

Having worked in ML at two different companies now, I think that people interpreting model output as intelligence or understanding says much more about the people than about the model output. We want it to be true, so we squint and connect dots and it's true. But it isn't. It's math and tricks, and if human intelligence is truly nothing more than math and tricks, then what we have today is a tiny, tiny, tiny fraction…

> Having worked in ML at two different companies now, I think that people interpreting model output as intelligence or understanding says much more about the people than about the model output.

I'd add it says a lot about all the companies that advertise them in a way that has nothing to do with reality, and those who actually buy them. We all know the usefulness of these things is below zero, because they only get in the way of getting actual help. And yet, someone's marketing department convinces a decision maker at another place they should implement this useless widget on their website, and that it will reduce the cost of customer service by X%. And they believe them.

Re: Chatbots: Still dumb after all these years

#74

Post by manquer »

prashantsengar wrote: post #58

I use chatbots to search for pages on websites where search is otherwise broken, like one of my bank's. I have never found a good use for them. They were once advertised to help your granny use the website but I haven't met a chatbot that could help me do something.

Sadly conversational UI is poorly implemented(studied?) area of UX. Even more than text it could be the most intutive way we communicate, far better than GUIs, however the space has been ruined with bad products promising the moon without putting effort to the buyer and delivering nothing to the user.

You could build chatbot with just a lot of grunt work and if else conditions and basic language parsing. Sadly no one does that , most chatbots today are low effort solutions that basically ingest random content and expect the model to learn and magically solve problems, which ofcourse does not happen as the model doesn't actually understand anything.

Re: Chatbots: Still dumb after all these years

#75

Post by RedBeetDeadpool »

specialp wrote: post #66
antux wrote: post #53

Chatbots were trendy because people thought they were AI and could do the same work as a human. They were wrong and now chatbots have become nothing but a fad. What's more useful are live chats where users can contact someone for help live on a chat screen. This is the future, not stupid chatbots.

The issue becomes when the human at the other end of a chat or phone conversation is limited to the same fixed set of responses and solutions that the bot is. So, they in effect become not much better than the bot because they are not allowed to use any non-scripted actions or reasoning. I have been encountering that more and more.

Are you saying you had problems with Comcast more and more? because that's what I'm hearing.

Re: Chatbots: Still dumb after all these years

#77

Post by lgeorget »

tobyjsullivan wrote: post #43
arthur_sav wrote: post #5

I really hate when companies hide behind chatbots. Like, NOOOO, your "AI" chatbot didn't help me - get me an actual person.

Kind of a weird tangent but I had a very interesting experience with one of these customer support chatbots recently. My ISP apparently now requires that all customers communicate with their chatbot as the only point of contact. So, naturally, I was pseudo-outraged because I know chatbots are just a money-saving gimmick that reduces workload by driving away 80% of support requests regardless of whether they actually…

I share the sentiment, I feel like if you have a long FAQ or list of help articles, a chatbot can actually make a good search engine. Contrarily to conventional search engines, it won't trip over synonyms or formulations not found as-is in the knowledge base.

Re: Chatbots: Still dumb after all these years

#78

Post by acidburnNSA »

In the early 1990s, Sound Blaster Pro sound cards came with a "psychiatrist" chat bot called Dr. SBAITSO which would reply in text and actually speak it out loud (showcasing the TTS). As a kid, I thought it was amazing, and I spent countless hours trying to converse with it. From a superficial level, modern chat bots seem roughly as good as the old doc.

Re: Chatbots: Still dumb after all these years

#79

Post by acdha »

OJFord wrote: post #60
tobyjsullivan wrote: post #43

Earlier quoted context omitted.

Kind of a weird tangent but I had a very interesting experience with one of these customer support chatbots recently. My ISP apparently now requires that all customers communicate with their chatbot as the only point of contact. So, naturally, I was pseudo-outraged because I know chatbots are just a money-saving gimmick that reduces workload by driving away 80% of support requests regardless of whether they actually…

> Long story short, I proposed the question to the chatbot in all its complexity, assuming it would be handed over to a human agent to read the transcript. The chatbot immediately understood the question and provided the exact response I needed. How do you know it did? I.e. that a human it was passed to didn't just pass your inverted Turing test!

This is one of the big confounds: a lot of the companies which brag about AI prowess are relying on a bunch of generally not well paid humans to cover the gaps.
Post reply on HN